Passer à la navigation principale Passer à la recherche Passer au contenu principal

Monge, Bregman and Occam: Interpretable Optimal Transport in High-Dimensions with Feature-Sparse Maps

  • Apple Computer

Résultats de recherche: Contribution à un journal › Article de conférence › Revue par des pairs

12 Citations (Scopus)

Résumé

Optimal transport (OT) theory focuses, among all maps T : ℝd → ℝd that can morph a probability measure onto another, on those that are the “thriftiest”, i.e. such that the averaged cost c(x, T(x)) between x and its image T(x) be as small as possible. Many computational approaches have been proposed to estimate such Monge maps when c is the ℓ22 distance, e.g., using entropic maps (Pooladian and Niles-Weed, 2021), or neural networks (Makkuva et al., 2020; Korotin et al., 2020). We propose a new model for transport maps, built on a family of translation invariant costs c(x, y):= h(x - y), where h := 1/2 ∥ · ∥2/2 + τ and τ is a regularizer. We propose a generalization of the entropic map suitable for h, and highlight a surprising link tying it with the Bregman centroids of the divergence Dh generated by h, and the proximal operator of τ. We show that choosing a sparsity-inducing norm for τ results in maps that apply Occam's razor to transport, in the sense that the displacement vectors ∆(x):= T(x) - x they induce are sparse, with a sparsity pattern that varies depending on x. We showcase the ability of our method to estimate meaningful OT maps for high-dimensional single-cell transcription data, in the 34000-d space of gene counts for cells, without using dimensionality reduction, thus retaining the ability to interpret all displacements at the gene level.

langue originaleAnglais
Pages (de - à)6671-6682
Nombre de pages12
journalProceedings of Machine Learning Research
Volume202
étatPublié - 1 janv. 2023
Modification externeOui
Evénement40th International Conference on Machine Learning, ICML 2023 - Honolulu, États-Unis
Durée: 23 juil. 2023 → 29 juil. 2023

Empreinte digitale

Examiner les sujets de recherche de « Monge, Bregman and Occam: Interpretable Optimal Transport in High-Dimensions with Feature-Sparse Maps ». Ensemble, ils forment une empreinte digitale unique.

Contient cette citation